© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118727
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     применение
    -0.06
     использование
    -0.06
    риста
    -0.06
     utilizar
    -0.06
     استفاده
    -0.06
     пайда
    -0.06
    stap
    -0.06
    运用
    -0.06
     द्वारा
    -0.06
     vorhanden
    -0.05
    POSITIVE LOGITS
     sensing
    0.07
     like
    0.06
     Mention
    0.06
     because
    0.06
    封闭
    0.06
    It
    0.06
    instead
    0.06
     Instead
    0.06
    你也
    0.06
    নিতে
    0.05
    Activations Density 0.000%

    No Known Activations